diff --git a/scripts/ci/strix_quick_gate.sh b/scripts/ci/strix_quick_gate.sh
index 337373001..ae324f44c 100755
--- a/scripts/ci/strix_quick_gate.sh
+++ b/scripts/ci/strix_quick_gate.sh
@@ -221,7 +221,8 @@ has_strix_report_failure_signal() {
 			report_root="$newest_report_root"
 		fi
 		while IFS= read -r -d '' report_log; do
-			if grep -Eiq '(^|[^[:alpha:]])(Fatal|Denied|Warn|Warning|WARNING|Timeout)([^[:alpha:]]|$)' "$report_log"; then
+			if has_unexpected_strix_failure_signal_file "$report_log" ||
+				grep -Eiq '(^|[^[:alpha:]])Timeout([^[:alpha:]]|$)' "$report_log"; then
 				return 0
 			fi
 		done < <(find "$report_root" -type f -name '*.log' -print0)
@@ -3150,8 +3151,29 @@ is_llm_token_limit_error() {
 # errors (timeout, rate-limit, transport failures) that indicate the scan
 # was interrupted or incomplete.  Used as a guard to prevent the
 # below-threshold override from silently passing an aborted scan.
+has_unexpected_strix_failure_signal_file() {
+	local signal_file="$1"
+	local signal_line
+	while IFS= read -r signal_line; do
+		# Strix emits this exact decorative banner for supported models that are
+		# not on its recommended frontier list. It is a quality advisory, not
+		# evidence that provider execution or the scan was incomplete.
+		if printf '%s\n' "$signal_line" |
+			grep -Eq '^[^[:alnum:]]*MODEL QUALITY WARNING[^[:alnum:]]*$'; then
+			continue
+		fi
+		return 0
+	done < <(grep -Ei '(^|[^[:alpha:]])(Fatal|Denied|Warn|Warning)([^[:alpha:]]|$)' "$signal_file" || true)
+
+	return 1
+}
+
+has_unexpected_strix_console_failure_signal() {
+	has_unexpected_strix_failure_signal_file "$STRIX_LOG"
+}
+
 has_detected_infrastructure_error() {
-	if grep -Eiq '(^|[^[:alpha:]])(Fatal|Denied|Warn|Warning)([^[:alpha:]]|$)' "$STRIX_LOG"; then
+	if has_unexpected_strix_console_failure_signal; then
 		return 0
 	fi
 
diff --git a/scripts/ci/test_strix_quick_gate.sh b/scripts/ci/test_strix_quick_gate.sh
index bf0a8693e..cb6abea20 100755
--- a/scripts/ci/test_strix_quick_gate.sh
+++ b/scripts/ci/test_strix_quick_gate.sh
@@ -4467,6 +4467,37 @@ EOS
 			;;
 		esac
 		;;
+	nim-primary-rate-limit-clean-fallback-quality-warning|nim-primary-rate-limit-clean-fallback-quality-report-warning)
+		case "${STRIX_LLM:-}" in
+		nvidia_nim/nvidia/nemotron-3-super-120b-a12b)
+			echo "LLM CONNECTION FAILED"
+			echo "Error: litellm.RateLimitError: Nvidia_nimException - Error code: 429"
+			exit 1
+			;;
+		nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5)
+			echo "╭─ STRIX ──────────────────────────────────────────────────────────────────────╮"
+			echo "│  MODEL QUALITY WARNING                                                       │"
+			echo "│  'nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5' is not a recommended  │"
+			echo "│  frontier model for Strix.                                                   │"
+			echo "│  You can continue, but weaker models may miss vulnerabilities or produce     │"
+			echo "│  lower-quality findings.                                                     │"
+			if [ "${FAKE_STRIX_SCENARIO:?}" = "nim-primary-rate-limit-clean-fallback-quality-report-warning" ]; then
+				mkdir -p "$STRIX_REPORTS_DIR/fake-nim-quality-advisory"
+				cat >"$STRIX_REPORTS_DIR/fake-nim-quality-advisory/strix.log" <<'EOS'
+│  MODEL QUALITY WARNING                                                       │
+2026-08-23 12:32:17.984 INFO strix-pr-scope-example - strix.tools.finish.tool: finish_scan: completed scan with 0 vulnerability report(s)
+EOS
+			fi
+			echo "│  Vulnerabilities 0                                                           │"
+			echo "╰──────────────────────────────────────────────────────────────────────────────╯"
+			exit 0
+			;;
+		*)
+			echo "Error: NIM quality-warning fallback path unexpected (${STRIX_LLM:-})" >&2
+			exit 62
+			;;
+		esac
+		;;
 	provider-fatal-success-signal)
 		echo "Fatal: provider stream aborted"
 		exit 0
@@ -6363,6 +6394,37 @@ run_filtered_gate_case_if_requested() {
 		"vertex_ai/report-known-internal-warning-sanitized" \
 		"<unset>"
 		;;
+	nim-primary-rate-limit-clean-fallback-quality-warning | nim-primary-rate-limit-clean-fallback-quality-report-warning)
+		run_gate_case "$STRIX_TEST_CASE_FILTER" \
+			"nvidia_nim/nvidia/nemotron-3-super-120b-a12b" \
+			"" \
+			"0" \
+			"REGEX:Strix quick scan succeeded with fallback model 'nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5' in [0-9]+s\\." \
+			"2" \
+			"nvidia_nim/nvidia/nemotron-3-super-120b-a12b|nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5" \
+			"https://integrate.api.nvidia.com/v1|https://integrate.api.nvidia.com/v1" \
+			"nvidia_nim" \
+			"https://integrate.api.nvidia.com/v1" \
+			"" \
+			"0" \
+			"CRITICAL" \
+			"0" \
+			"" \
+			"" \
+			"1200" \
+			"0" \
+			"" \
+			"" \
+			"" \
+			"" \
+			"0" \
+			"" \
+			"" \
+			"" \
+			"__SAME_AS_FALLBACK_MODELS__" \
+			"nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5" \
+			"1"
+		;;
 	provider-fatal-success-signal | provider-warning-success-signal)
 		run_gate_case "$STRIX_TEST_CASE_FILTER" \
 		"vertex_ai/$STRIX_TEST_CASE_FILTER" \
@@ -10330,6 +10392,66 @@ run_gate_case "strict-zero-findings-timeout-fails-pr" \
 	"" \
 	"1"
 
+run_gate_case "nim-primary-rate-limit-clean-fallback-quality-warning" \
+	"nvidia_nim/nvidia/nemotron-3-super-120b-a12b" \
+	"" \
+	"0" \
+	"REGEX:Strix quick scan succeeded with fallback model 'nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5' in [0-9]+s\\." \
+	"2" \
+	"nvidia_nim/nvidia/nemotron-3-super-120b-a12b|nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5" \
+	"https://integrate.api.nvidia.com/v1|https://integrate.api.nvidia.com/v1" \
+	"nvidia_nim" \
+	"https://integrate.api.nvidia.com/v1" \
+	"" \
+	"0" \
+	"CRITICAL" \
+	"0" \
+	"" \
+	"" \
+	"1200" \
+	"0" \
+	"" \
+	"" \
+	"" \
+	"" \
+	"0" \
+	"" \
+	"" \
+	"" \
+	"__SAME_AS_FALLBACK_MODELS__" \
+	"nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5" \
+	"1"
+
+run_gate_case "nim-primary-rate-limit-clean-fallback-quality-report-warning" \
+	"nvidia_nim/nvidia/nemotron-3-super-120b-a12b" \
+	"" \
+	"0" \
+	"REGEX:Strix quick scan succeeded with fallback model 'nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5' in [0-9]+s\\." \
+	"2" \
+	"nvidia_nim/nvidia/nemotron-3-super-120b-a12b|nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5" \
+	"https://integrate.api.nvidia.com/v1|https://integrate.api.nvidia.com/v1" \
+	"nvidia_nim" \
+	"https://integrate.api.nvidia.com/v1" \
+	"" \
+	"0" \
+	"CRITICAL" \
+	"0" \
+	"" \
+	"" \
+	"1200" \
+	"0" \
+	"" \
+	"" \
+	"" \
+	"" \
+	"0" \
+	"" \
+	"" \
+	"" \
+	"__SAME_AS_FALLBACK_MODELS__" \
+	"nvidia_nim/nvidia/llama-3.3-nemotron-super-49b-v1.5" \
+	"1"
+
 run_gate_case "provider-fatal-success-signal" \
 	"vertex_ai/provider-fatal-success-signal" \
 	"" \